Feature, Alignment, and Supervision in Category Learning: A Comparative Approach with Children and Neural Networks
This work addresses the problem of understanding human and machine learning from sparse data for cognitive science and machine learning researchers, but it is incremental as it builds on existing comparative approaches.
The study compared children and convolutional neural networks (CNNs) in a few-shot semi-supervised category learning task, finding that children generalize quickly from minimal labels with feature-specific biases, while CNNs benefit more from added supervision depending on alignment and feature structure.
Understanding how humans and machines learn from sparse data is central to cognitive science and machine learning. Using a species-fair design, we compare children and convolutional neural networks (CNNs) in a few-shot semi-supervised category learning task. Both learners are exposed to novel object categories under identical conditions. Learners receive mixtures of labeled and unlabeled exemplars while we vary supervision (1/3/6 labels), target feature (size, shape, pattern), and perceptual alignment (high/low). We find that children generalize rapidly from minimal labels but show strong feature-specific biases and sensitivity to alignment. CNNs show a different interaction profile: added supervision improves performance, but both alignment and feature structure moderate the impact additional supervision has on learning. These results show that human-model comparisons must be drawn under the right conditions, emphasizing interactions among supervision, feature structure, and alignment rather than overall accuracy.